Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1157 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1773308 (The Pile)

Max Activating Token Index: 683

Text #1

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1239907 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2572. Min Act: -0.0000

Data Index: 703121 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1308549 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1693662 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1973. Min Act: -0.0000

Data Index: 905490 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1479. Min Act: -0.0000

Data Index: 399493 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1876323 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1368. Min Act: -0.0000

Data Index: 74794 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1531916 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1271. Min Act: -0.0000

Data Index: 744161 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1102783 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0983. Min Act: -0.0000

Data Index: 335004 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1024812 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1250. Min Act: -0.0000

Data Index: 78861 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1184. Min Act: -0.0000

Data Index: 663051 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1189. Min Act: -0.0000

Data Index: 142861 (The Pile)

Max Activating Token Index: 650

Text #17

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1257. Min Act: -0.0000

Data Index: 537340 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1098056 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 1.2813. Min Range: -1.2813

Max Act: 1.0940. Min Act: -0.0000

Data Index: 583141 (The Pile)

Max Activating Token Index: 133